Datasets and vector search
Understand which comparative corpora are available and what similarity results mean.
What you will be able to do
- Select an appropriate dataset
- Run a similarity search
- Trace a result back to its source chunk
The basic route
- 01
Choose the collection
Use only corpora relevant to the question and check their date, language and licence.
- 02
Search by similarity
Treat the ranking as a retrieval aid, not proof of historical relationship.
- 03
Open the source
Read the full source context before adding a comparison to the research record.
Before you begin
- A defined comparison question
- Access to the required dataset